Extreme Value Statistics - Virtual Classroom

Date: Wednesday 02 December 2020, 9.30AM
Location: Online
CPD: 12.0 hours
RSS Training


Share this event

Most statistical methods are aimed at characterizing expected values, but in many settings it is the unexpected values, the extremes or outliers, that are of interest - e.g. extreme weather events, rare drug toxicities, or extreme movements in financial markets. This is an introductory course in Extreme Value Statistics, focusing mostly on univariate methods but including some multivariate modelling topics. We will cover the theory and associated statistical methods which form a cornerstone of natural hazard risk planning and engineering design safety, and which enable extrapolation to levels beyond those already observed in a dataset. We describe current best practice and step-by-step implementation of methods for calculating high quantiles and associated uncertainties.  We address topical challenges arising from non-stationarity in processes. The ideas are illustrated throughout by using detailed worked examples from environmental risk assessment, financial and clinical-safety applications.  All of the topics covered are accompanied by hands-on computer tutorials in R, so that participants will carry out themselves a complete set of worked examples throughout the course.

Please note: Bookings will close 4 working days before the course start date or when the course has reached its maximum capacity.
 

Course Outline

Most statistical methods are aimed at characterizing expected values, but in many settings it is the unexpected values, the extremes or outliers, that are of interest - e.g. extreme weather events, rare drug toxicities, or extreme movements in financial markets. This is an introductory course in Extreme Value Statistics, focusing mostly on univariate methods but including some multivariate modelling topics. We will cover the theory and associated statistical methods which form a cornerstone of natural hazard risk planning and engineering design safety, and which enable extrapolation to levels beyond those already observed in a dataset. We describe current best practice and step-by-step implementation of methods for calculating high quantiles and associated uncertainties.  We address topical challenges arising from non-stationarity in processes. The ideas are illustrated throughout by using detailed worked examples from environmental risk assessment, financial and clinical-safety applications.  All of the topics covered are accompanied by hands-on computer tutorials in R, so that participants will carry out themselves a complete set of worked examples throughout the course.
 

Learning Outcomes

By attending this course, attendees can hope to gain the following:

  • Solid understanding of the theory and best practice to support their own independent use of Extreme Value Statistics;

  • Detailed step-by-step methods for systematic Extreme Value Modelling and computation of high quantiles and extreme values;

  • Practical experience of using state of the art software to carry out Extreme Value Analysis for themselves, with a complete set of worked examples and accompanying code.
     

Topics Covered

  • Motivating examples

  • Introduction to univariate Extreme Value Theory

  • Modelling process maxima and threshold excesses

  • Using diagnostic tools for efficient threshold selection

  • Addressing non-stationarity by using covariates in EV models

  • Dealing with serial dependence in data

  • Extensive worked examples from environmental hazard, finance, offshore and clinical trials settings

  • Modelling multivariate extreme values
     

Target Audience

As well as statisticians and quantitative researchers these may include but are not limited to structural design engineers, metocean scientists, offshore engineers, re/insurance natural peril defence planners, environmental consultancies, pharmaceutical companies, clinical trial safety regulators, financial risk managers.


Assumed Knowledge

It is assumed that delegates are Statistically literate with familiarity of statistical modelling techinques equivalent to undergraduate level statistics, including likelihood based inference (ideally including Bayesian) and regression modelling. The course assumes no previous knowledge of Extreme Value Statistics, but requires a general familiarity with statistical modelling techniques equivalent to undergraduate level statistics. Course workshops will use R, knowledge of which would be an advantage, however this is not a necessity since all required code will be supplied in the accompanying course notes.

 

Dr Janet Heffernan

Janet is an Independent statistical consultant with a wealth of experience training users of statistics in a broad range of topics, but specialising in Extreme Value Statistics.  She has delivered bespoke courses in this area to a range of industry customers.  Whilst lecturer in the Extreme Values group at Lancaster University, some of her work appeared as a Read Paper in JRSS Series B. Her sizeable number of publications in this field, both theoretical and applied, include applications as diverse as clinical safety, rainfall, sea levels, air pollution, and bulk-carrier safety. She continues to work on substantive applications in Extremes with a variety of industry clients.
 

Dr Harry Southworth

Dr Harry Southworth won the RSS/PSI award for excellence in the pharmaceutical industry in 2012 for his work in applying extreme values methods to clinical trial safety data. Besides extreme value modelling, Harry's other specialities are in data visualization and data mining. Harry has 17 years' experience in the pharmaceutical industry and is currently working for his own company, Data Clarity Consulting Ltd.

 

Fees

   

Registration before
 2 November 2020

 

Registration on/after
 2 November 2020

                                  


Non Member 

RSS Fellow 

RSS CStat/Gradstat/Data Analyst 
also MIS & FIS

 

£611.00+vat 

£520.00+vat 

£490.00+vat

£680.00+vat 

£577.00+vat 

£543.00+vat